From 292c1cab940d88416e54254e84d0ef158cb84e81 Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Thu, 25 Jun 2026 07:04:06 +0000
Subject: [PATCH] fix(llama-cpp,turboquant): only CPU_ALL_VARIANTS for pure-CPU
 builds, GPU uses fallback

The previous gate sent every non-hipblas build through llama-cpp-cpu-all, so the
GPU image builds (cublas, sycl_f16/f32, vulkan, nvidia l4t) compiled the whole CPU
microarch variant matrix on top of their already-huge GPU backend - blowing the
build time (the sycl job was only 59% done after 2h11m) - and the arm64 l4t build
failed at `apt-get install gcc-14` (exit 100) on the Jetson base.

Gate on an empty BUILD_TYPE instead: only the pure CPU image (build-type: '' in
.github/backend-matrix.yml) builds the CPU_ALL_VARIANTS set; every GPU build gets a
single fallback CPU grpc-server, since the accelerator does the compute. This also
confines the arm64 gcc-14 step (needed for the armv9.2 SME variants) to the CPU
build, away from the GPU base images.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
---
 .docker/llama-cpp-compile.sh  | 26 +++++++++++++++-----------
 .docker/turboquant-compile.sh | 14 ++++++++------
 2 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/.docker/llama-cpp-compile.sh b/.docker/llama-cpp-compile.sh
index 776a2cceb..647a1c448 100755
--- a/.docker/llama-cpp-compile.sh
+++ b/.docker/llama-cpp-compile.sh
@@ -18,22 +18,26 @@ if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
 fi
 
 cd /LocalAI/backend/cpp/llama-cpp
-if [ "${BUILD_TYPE}" = "hipblas" ]; then
-  # ROCm: the GPU does the compute, so a single fallback CPU build is enough.
-  make llama-cpp-fallback
-else
-  # arm64: ggml's CPU_ALL_VARIANTS table includes armv9.2 SME variants whose
-  # -march=...+sme is rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so
-  # build the arm64 variants with gcc-14 (the host never *selects* SME unless it has it,
-  # but every variant must still compile).
+if [ -z "${BUILD_TYPE:-}" ]; then
+  # Pure CPU image (BUILD_TYPE empty): one build with ggml CPU_ALL_VARIANTS replaces the
+  # per-microarch binaries (x86: avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). ggml
+  # dlopens the best libggml-cpu-*.so at runtime by probing host CPU features.
+  #
+  # arm64: the CPU_ALL_VARIANTS table includes armv9.2 SME variants whose -march=...+sme is
+  # rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so build the arm64
+  # variants with it (the host never *selects* SME unless it has it, but every variant must
+  # still compile).
   if [ "${TARGETARCH}" = "arm64" ]; then
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi
-  # x86 and arm64: one build with ggml CPU_ALL_VARIANTS replaces the per-microarch
-  # binaries (x86: avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). ggml dlopens the
-  # best libggml-cpu-*.so at runtime by probing host CPU features.
   make llama-cpp-cpu-all
+else
+  # GPU build (cublas/hipblas/sycl/vulkan/...): the accelerator does the compute, so a
+  # single fallback CPU build is enough - no per-microarch CPU variants needed. (This also
+  # keeps the heavy GPU backend compile from also building the whole CPU variant matrix,
+  # and avoids the gcc-14 apt step on GPU base images such as nvidia l4t.)
+  make llama-cpp-fallback
 fi
 make llama-cpp-grpc
 make llama-cpp-rpc-server
diff --git a/.docker/turboquant-compile.sh b/.docker/turboquant-compile.sh
index baf814c7e..ca6cf2690 100755
--- a/.docker/turboquant-compile.sh
+++ b/.docker/turboquant-compile.sh
@@ -19,17 +19,19 @@ fi
 
 cd /LocalAI/backend/cpp/turboquant
 
-if [ "${BUILD_TYPE}" = "hipblas" ]; then
-  # ROCm: single fallback CPU build (GPU does the compute).
-  make turboquant-fallback
-else
-  # arm64: the CPU_ALL_VARIANTS armv9.2 SME variants need gcc-14 (gcc-13 rejects +sme).
+if [ -z "${BUILD_TYPE:-}" ]; then
+  # Pure CPU image: one ggml CPU_ALL_VARIANTS build replaces the per-microarch binaries.
+  # arm64: the armv9.2 SME variants need gcc-14 (gcc-13 rejects +sme).
   if [ "${TARGETARCH}" = "arm64" ]; then
     apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
     export CC=gcc-14 CXX=g++-14
   fi
-  # x86 and arm64: one ggml CPU_ALL_VARIANTS build replaces the per-microarch binaries.
   make turboquant-cpu-all
+else
+  # GPU build (cublas/hipblas/sycl/vulkan/...): single fallback CPU build, the accelerator
+  # does the compute. Keeps the GPU compile from also building the CPU variant matrix and
+  # avoids the gcc-14 apt step on GPU base images such as nvidia l4t.
+  make turboquant-fallback
 fi
 make turboquant-grpc
 make turboquant-rpc-server